CN102622886B - Video-based method for detecting violation lane-changing incident of vehicle - Google Patents
Video-based method for detecting violation lane-changing incident of vehicle Download PDFInfo
- Publication number
- CN102622886B CN102622886B CN201210080262.4A CN201210080262A CN102622886B CN 102622886 B CN102622886 B CN 102622886B CN 201210080262 A CN201210080262 A CN 201210080262A CN 102622886 B CN102622886 B CN 102622886B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- threshold value
- field picture
- video
- lane
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video-based method for detecting a violation lane-changing incident of a vehicle. The method mainly comprises the steps of: separating a target background in each frame of image in video to be treated through block-based binarization segmentation, selecting a block-based characteristic angular point, tracking a vehicle through a characteristic point of labeling a target, recording position information of the tracking point, and calculating a vehicle position proportional variance on the basis of a tracking track characteristic so that whether a vehicle changes a lane is judged. Compared with the prior art, the method provided by the invention can be used for detecting all vehicle targets in a video range without being limited by the environment and judging real-time video, has the advantages of short detection time, easy implementation and higher accuracy, is very suitable for detecting the violation lane-changing incident of the vehicle in real time, and has wide application prospect.
Description
Technical field
The invention belongs to video detection technology field, be specifically related to a kind of vehicle peccancy lane change event detecting method based on video.
Background technology
In recent years, along with economic fast development, road traffic construction also develops rapidly, and the motor vehicle volume of holding is also soaring rapidly simultaneously.Current Transportation Infrastructure Construction and traffic law are universal all relatively lag behind in the situation that, communications and transportation problem is day by day serious, and traffic hazard takes place frequently, urban traffic congestion, and traffic environment constantly worsens.Statistical data shows, approximately the traffic hazard of 70%-80% is by driver, the undesired driving behavior of vehicle to be caused, and comprises that driver violation is driven, fatigue driving etc.Therefore, in order to create better traffic environment, to the detection of these vehicle peccancy behaviors, be, the most important thing.
Vehicle peccancy lane change refers to that vehicle is in a certain lanes, and due to certain situation, lane change is travelled in parallel another adjacent track.The danger of this traffic behavior is very large, easily causes traffic congestion, even leads to traffic hazard, makes troubles and danger to people's life.Traditional vehicle lane change event detecting method mainly contains electronic coil detection method, digital video detection method.Wherein electronic coil method poor expandability, must suspend traffic, destroy road surface during installation and maintenance, and these methods can not be used widely in real life.
Along with the generally use of vehicle monitoring system, the transport information detection technique based on video is more and more subject to everybody attention.Current new project adopts installation more and more, safeguard do not need to destroy roadbed, surveyed area large, implement the convenient, flexible transport information detection technique based on video.Vehicle lane change detection method based on video becomes the focus of research, although these methods can realize vehicle peccancy lane change affair alarm, the complex disposal process of video data, poor reliability, the requirement of real-time of detection can not be met, the requirement of practical application cannot be met.
Summary of the invention
Defect or deficiency for prior art, the object of the invention is to, and a kind of vehicle peccancy lane change event detecting method based on video is provided, and the method can realize in real time, detect reliably all vehicular events in range of video.
In order to realize above-mentioned task, the present invention takes following technical solution:
A vehicle peccancy lane change event detecting method based on video, is characterized in that, the method is implemented according to the following step:
Step 1, calibration vehicle diatom arranges barrier line in road, finds out the particular location in track simultaneously, calculates the horizontal pixel width of the every a line of its right-hand lane, usings this as benchmark lane width;
Step 2 is all divided into a plurality of by the first two field picture and background image under identical piece coordinate system.Each piece to the first two field picture finds the background piece identical with this tile position in background image, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of this piece;
When the absolute value of gained is greater than the threshold value of setting, this piece is object block, and the gray-scale value that the inner all pixels of this piece are set is 255;
When the absolute value of gained is less than or equal to the threshold value of setting, this piece is background piece, and the gray-scale value that the inner all pixels of this piece are set is 0;
Finally the background in the first two field picture and target are separated, obtained the binary image of the first two field picture;
Step 3, carries out rim detection to the binary image of the first two field picture, finds best angle point,, when laterally detecting data and longitudinally detection data are greater than a certain threshold value simultaneously, retains these corner location:
Step 4, the characteristic information using the position of these angle points as vehicle creates an object construction body simultaneously, records particular location and the coupling lock-on counter information of these vehicle targets, and coupling lock-on counter is initialized as zero for the first time;
Step 5, carries out corners Matching, searches out matched position, and coupling lock-on counter adds one;
Step 6, to the second frame, the 3rd two field picture ..., m two field picture, repeating step two, step 3, step 5 are processed, and to take the corner location of the first frame (former frame) record be foundation, compare with the corner location of the target of record in the second frame (present frame), when both positions, absolute value difference is greater than certain threshold value, just thinks new vehicle target in this second frame (current), according to step 4, process again
Step 7, when coupling tracker is greater than a certain threshold value, the position that coordinate in the pursuit path of calculating vehicle mates angle point, and the horizontal algebraic distance between corresponding line No striding lane line, calculate the ratio between these horizontal algebraic distances and corresponding line benchmark lane width, the fluctuation size of judgement gained vehicle location ratio, namely usings the Rule of judgment of vehicle location ratio variance size as lane change event, when this ratio variance is greater than a certain threshold value, think vehicle lane change.
Wherein:
Threshold value described in step 2 is the area of the area～60 * piece of 50 * piece.
Threshold value described in step 3 is 180～220;
Threshold value described in step 6 is 5～20;
The threshold value span of the coupling tracker described in step 7 is 70～90, the threshold value span 0.15 of ratio variance.
Vehicle peccancy lane change event detecting method based on video of the present invention, compared with prior art, can detect all vehicle targets in range of video, be not subject to environmental restraint, can detect real-time video, and detection time is short, be easy to realize, accuracy is higher, is well suited for real-time detection vehicle lane change event, has broad application prospects.
Accompanying drawing explanation
Fig. 1 is for demarcating the background image in track;
Fig. 2 is a two field picture in normal video---354 two field pictures;
Fig. 3 is 354 two field pictures of marker characteristic angle point;
Fig. 4 is for drawing the 404th frame video image of tracker wire;
Fig. 5 is for drawing the 454th two field picture of tracker wire.
Fig. 6 is for drawing the 502nd two field picture of tracker wire.
Fig. 7 is for marking the 454th two field picture that needs to calculate variable
Below in conjunction with drawings and Examples, the present invention is described in further detail.
Embodiment
Referring to accompanying drawing, the present embodiment provides a kind of object lesson of the vehicle peccancy lane change event detecting method based on video, in its process handled image be in video along positive seasonal effect in time series the first two field picture, the second two field picture, the 3rd two field picture ..., m (m is natural number) two field picture.
The concrete following steps that adopt realize:
Step 1, calibration vehicle diatom arranges barrier line in road, finds out the particular location in track simultaneously, calculates the horizontal pixel width of the every a line of its right-hand lane, usings this as benchmark lane width;
Step 2 is all divided into a plurality of by the first two field picture and background image under identical piece coordinate system.Each piece to the first two field picture finds the background piece identical with this tile position in background image, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of this piece;
When the absolute value of gained is greater than the threshold value of setting, this piece is object block, and the gray-scale value that the inner all pixels of this piece are set is 255; The area of area～60 * piece that threshold value span is wherein 50 * piece, i.e. 50 * (w * h)～60 * (w * h); Wherein w is the width in piece region, the height that h is piece.
When the absolute value of gained is less than or equal to the threshold value of setting, this piece is background piece, and the gray-scale value that the inner all pixels of this piece are set is 0;
Finally the background in the first two field picture and target are separated, obtained the binary image of the first two field picture;
Step 3, carries out rim detection to the binary image of the first two field picture, finds best angle point,, when laterally detecting data and longitudinally detection data are greater than a certain threshold value simultaneously, retains these corner location;
Threshold value span 180～220 wherein;
Step 4, the characteristic information using the position of these angle points as vehicle creates an object construction body simultaneously, records particular location and the coupling lock-on counter information of these vehicle targets, and coupling lock-on counter is initialized as zero for the first time;
Step 5, carries out corners Matching, searches out matched position, and coupling lock-on counter adds one;
Step 6, to the second two field picture, the 3rd two field picture ..., m two field picture, according to step 2, step 3, step 5, process, and to take the corner location of the first frame (former frame) record be foundation, compare with the corner location of the target of record in the second frame (present frame), when both positions, absolute value difference is greater than certain threshold value, just thinks new vehicle target in this second frame (present frame), according to step 4, process again
Step 7, when coupling tracker is greater than a certain threshold value, the position that coordinate in the pursuit path of calculating vehicle mates angle point, and the horizontal algebraic distance between corresponding line No striding lane line, calculate the NormL ratio between these horizontal algebraic distance L and corresponding line benchmark lane width, the fluctuation size of judgement gained vehicle location ratio, namely using the Rule of judgment of vehicle location ratio variance size as lane change event, when this ratio variance is greater than a certain threshold value, think vehicle lane change.
The threshold value span of coupling tracker is wherein 70～90, the threshold value span 0.15 of ratio variance;
In conjunction with Fig. 2 and Fig. 3, the angle point of choosing in above-mentioned steps is illustrated, in binary image, there is a target, be obviously vehicle target, this target is done to rim detection, when horizontal and vertical, while satisfying condition, obtain angle point, as shown in Figure 2 simultaneously.
In conjunction with Fig. 7, lane change in above-mentioned steps is detected and is illustrated, distance is the position that coordinate in the pursuit path of vehicle mates angle point, and the horizontal algebraic distance L (Point) between corresponding line No striding lane line, datum width is the horizontal pixel width NormL (Point) of the every a line of right-hand lane, when whole coordinates position of track, ratio variance on track is greater than threshold value, thinks that this vehicle lane change travels.
Embodiment:
Known video positive sowing time, target vehicle is marked in the 354th two field picture for the first time, and as Fig. 2, Fig. 3, in embodiment, in processing procedure, the sample frequency of video is that 25 frames are per second, two field picture size is 720 * 288, successively the 354th frame to the 454 two field pictures is processed according to the method described above.
As can be seen from Figure 7, target vehicle has been realized to 100 couplings and followed the tracks of, according to said method, can calculate target vehicle lane change and travel.
Claims (2)
1. the vehicle peccancy lane change event detecting method based on video, is characterized in that, the method is implemented according to the following step:
Step 1, calibration vehicle diatom arranges barrier line in road, finds out the particular location in track simultaneously, calculates the horizontal pixel width of the every a line of its right-hand lane, usings this as benchmark lane width;
Step 2 is all divided into a plurality of fritters by the first two field picture and background image under identical piece coordinate system; Each fritter to the first two field picture finds the background piece identical with tile position in background image, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of fritter;
When the absolute value of gained is greater than the threshold value of setting, fritter is object block, and the gray-scale value that the inner all pixels of fritter are set is 255;
When the absolute value of gained is less than or equal to the threshold value of setting, fritter is background piece, and the gray-scale value that the inner all pixels of fritter are set is 0;
Finally the background in the first two field picture and target are separated, obtained the binary image of the first two field picture;
Step 3, carries out rim detection to the binary image of the first two field picture, finds best angle point,, when laterally detecting data and longitudinally detection data are greater than a certain threshold value simultaneously, retains these corner location:
Step 4, the characteristic information using the position of these angle points as vehicle creates an object construction body simultaneously, records particular location and the coupling lock-on counter information of these vehicle targets, and coupling lock-on counter is initialized as zero for the first time;
Step 5, carries out corners Matching, searches out matched position, and coupling lock-on counter adds one;
Step 6, to the second two field picture, the 3rd two field picture ..., m two field picture, according to step 2, step 3, step 5, process, and to take the corner location of the first frame recording be foundation, compare with the corner location of the target of record in the second frame, when both positions, absolute value difference is greater than certain threshold value, just thinks new vehicle target in this second frame, then processes according to step 4;
Step 7, when coupling tracker is greater than a certain threshold value, the position that coordinate in the pursuit path of calculating vehicle mates angle point, and the horizontal algebraic distance between corresponding line No striding lane line, calculate the ratio between these horizontal algebraic distances and corresponding line benchmark lane width, the fluctuation size of judgement gained vehicle location ratio, namely usings the Rule of judgment of vehicle location ratio variance size as lane change event, when this ratio variance is greater than a certain threshold value, think vehicle lane change.
2. the method for claim 1, is characterized in that:
Threshold value described in step 2 is the area of the area～60 * piece of 50 * piece;
Threshold value described in step 3 is 180～220;
Threshold value described in step 6 is 5～20;
The threshold value span of the coupling tracker described in step 7 is 70～90, the threshold value span 0.15 of ratio variance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210080262.4A CN102622886B (en) | 2012-03-23 | 2012-03-23 | Video-based method for detecting violation lane-changing incident of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210080262.4A CN102622886B (en) | 2012-03-23 | 2012-03-23 | Video-based method for detecting violation lane-changing incident of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102622886A CN102622886A (en) | 2012-08-01 |
| CN102622886B true CN102622886B (en) | 2014-04-30 |
Family
ID=46562777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210080262.4A Expired - Fee Related CN102622886B (en) | 2012-03-23 | 2012-03-23 | Video-based method for detecting violation lane-changing incident of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102622886B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236158B (en) * | 2013-03-26 | 2015-06-24 | 中国公路工程咨询集团有限公司 | Method for warning traffic accidents in real time on basis of videos |
| CN103942960B (en) * | 2014-04-22 | 2016-09-21 | 深圳市宏电技术股份有限公司 | A kind of vehicle lane change detection method and device |
| CN104882005B (en) * | 2015-05-15 | 2017-07-04 | 青岛海信网络科技股份有限公司 | A kind of method and device for detecting lane flow amount |
| CN105632186B (en) * | 2016-03-11 | 2019-01-11 | 博康智能信息技术有限公司 | Detection vehicle is jumped a queue the method and apparatus of behavior |
| CN106250894B (en) * | 2016-07-26 | 2021-10-26 | 北京小米移动软件有限公司 | Card information identification method and device |
| CN107871393B (en) * | 2016-09-27 | 2021-06-04 | 千寻位置网络有限公司 | Method and system for automatically judging whether vehicle occupies prohibited lane in case of violation of regulations |
| CN106652445B (en) * | 2016-11-15 | 2019-08-23 | 成都通甲优博科技有限责任公司 | A kind of road traffic accident method of discrimination and device |
| CN109109862A (en) * | 2017-06-23 | 2019-01-01 | 上海汽车集团股份有限公司 | A kind of control method and device of the automatic lane-change of vehicle |
| CN107563310B (en) * | 2017-08-16 | 2020-06-16 | 电子科技大学 | Illegal lane change detection method |
| CN111028503B (en) * | 2018-10-09 | 2022-05-06 | 杭州海康威视系统技术有限公司 | Vehicle lane change monitoring method and device |
| CN109544909B (en) * | 2018-10-29 | 2021-06-04 | 华蓝设计（集团）有限公司 | Method for analyzing lane changing behavior of driver based on aerial video vehicle track |
| CN111243281A (en) * | 2018-11-09 | 2020-06-05 | 杭州海康威视系统技术有限公司 | Road multi-video joint detection system and detection method |
| CN109785640A (en) * | 2019-03-06 | 2019-05-21 | 南京邮电大学 | One kind is about vehicle violation detection system and its detection method |
| CN109887303B (en) * | 2019-04-18 | 2022-07-05 | 齐鲁工业大学 | Lane-changing behavior early warning system and method |
| CN110298300B (en) * | 2019-06-27 | 2022-11-22 | 上海工程技术大学 | Method for detecting vehicle illegal line pressing |
| CN111178224B (en) * | 2019-12-25 | 2024-04-05 | 浙江大华技术股份有限公司 | Object rule judging method, device, computer equipment and storage medium |
| CN111311960B (en) * | 2020-02-23 | 2021-07-27 | 长安大学 | Method for reminding occupied driving vehicle in tunnel section |
| CN111833598B (en) * | 2020-05-14 | 2022-07-05 | 山东科技大学 | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway |
| CN113836964B (en) * | 2020-06-08 | 2023-11-10 | 北京图森未来科技有限公司 | Method and device for detecting corner points of lane lines |
| CN114067570A (en) * | 2020-08-05 | 2022-02-18 | 北京万集科技股份有限公司 | Image acquisition equipment control method and device, computer equipment and storage medium |
| CN112053563B (en) * | 2020-09-16 | 2023-01-20 | 阿波罗智联(北京)科技有限公司 | Event detection method and device applicable to edge computing platform and cloud control platform |
| CN114613147B (en) * | 2020-11-25 | 2023-08-04 | 浙江宇视科技有限公司 | Vehicle violation identification method and device, medium and electronic equipment |
| JP2022126341A (en) * | 2021-02-18 | 2022-08-30 | 本田技研工業株式会社 | Vehicle control device, vehicle control method and program |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| CN101251927A (en) * | 2008-04-01 | 2008-08-27 | 东南大学 | Vehicle detecting and tracing method based on video technique |
| CN101872546A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video-based method for rapidly detecting transit vehicles |
| CN102110366A (en) * | 2011-03-28 | 2011-06-29 | 长安大学 | Block-based accumulated expressway vehicle parking event detecting method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030080878A1 (en) * | 2001-10-30 | 2003-05-01 | Kirmuss Charles Bruno | Event-based vehicle image capture |
-
2012
- 2012-03-23 CN CN201210080262.4A patent/CN102622886B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| CN101251927A (en) * | 2008-04-01 | 2008-08-27 | 东南大学 | Vehicle detecting and tracing method based on video technique |
| CN101872546A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video-based method for rapidly detecting transit vehicles |
| CN102110366A (en) * | 2011-03-28 | 2011-06-29 | 长安大学 | Block-based accumulated expressway vehicle parking event detecting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102622886A (en) | 2012-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102622886B (en) | Video-based method for detecting violation lane-changing incident of vehicle | |
| Zhao et al. | On-road vehicle trajectory collection and scene-based lane change analysis: Part i | |
| CN104575003B (en) | A kind of vehicle speed detection method based on traffic surveillance videos | |
| CN106297330B (en) | Reduce the method and system that pedestrian's street crossing influences plane perceptual signal control efficiency | |
| CN103730015B (en) | Intersection traffic flow detecting method and device | |
| CN104599502A (en) | Method for traffic flow statistics based on video monitoring | |
| CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN103425764B (en) | Vehicle matching method based on videos | |
| Song et al. | Vehicle behavior analysis using target motion trajectories | |
| CN109064495A (en) | A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique | |
| CN103150908B (en) | Average vehicle speed detecting method based on video | |
| CN103208190B (en) | Traffic flow detection method based on object detection | |
| CN102467821A (en) | Road distance detection method based on video image and apparatus thereof | |
| CN107038411A (en) | A kind of Roadside Parking behavior precise recognition method based on vehicle movement track in video | |
| CN102184547B (en) | Video-based vehicle reverse driving event detecting method | |
| CN108154146A (en) | A kind of car tracing method based on image identification | |
| CN105488485A (en) | Lane line automatic extraction method based on vehicle trajectory | |
| CN112084900A (en) | Underground garage random parking detection method based on video analysis | |
| CN107097794A (en) | The detecting system and its method of terrain vehicle diatom | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN103440785A (en) | Method for rapid lane departure warning | |
| CN109117702A (en) | The detection and count tracking method and system of target vehicle | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| Espino et al. | Rail extraction technique using gradient information and a priori shape model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140430 Termination date: 20160323 |